Kolloquium

.gitignore

@@ -1 +1,2 @@
 __pycache__/plot.cpython-311.pyc
+img/

app.py

@@ -2,17 +2,19 @@ import streamlit as st
 import torch
 from transformers import AutoTokenizer, AutoModelForTokenClassification
 from annotated_text import annotated_text
+from plot import Plot
+from flow import FlowChart
 import os
-from plot import Plot  # Assuming the class is saved in diagram_generator.py
 
 # Define initial threshold values at the top of the script
-default_cause_threshold = 20
+default_cause_threshold = 25
 default_indicator_threshold = 15
 default_cause_threshold_sankey = 20 
 default_indicator_threshold_sankey = 15 
 
 # Initialize Plots
 plot = Plot()
+flow_chart = FlowChart()
 
 # Load the trained model and tokenizer
 model_directory = "norygano/causalBERT"
@@ -33,7 +35,7 @@ st.markdown(
     """,
     unsafe_allow_html=True
 )
-st.markdown("[Weights](https://huggingface.co/norygano/causalBERT) | [Data](https://huggingface.co/datasets/norygano/causenv) | [Project](https://www.uni-trier.de/universitaet/fachbereiche-faecher/fachbereich-ii/faecher/germanistik/professurenfachteile/germanistische-linguistik/professoren/prof-dr-martin-wengeler/kontroverse-diskurse/individium-gesellschaft)")
+st.markdown("[Weights](https://huggingface.co/norygano/causalBERT) | [Data](https://huggingface.co/datasets/norygano/causenv)")
 st.write("Indicators and causes in explicit attributions of causality.")
 
 # Create tabs
@@ -151,4 +153,4 @@ with tab5:
         )
         indicator_threshold_sankey = st.slider(
             "Indicator >=", min_value=1, max_value=100, value=default_indicator_threshold_sankey, key="indicator_threshold_sankey"
-        )
+        )

flow.py

@@ -0,0 +1,76 @@
+import streamlit as st
+from streamlit_flow import streamlit_flow
+from streamlit_flow.elements import StreamlitFlowNode, StreamlitFlowEdge
+from streamlit_flow.state import StreamlitFlowState
+from streamlit_flow.layouts import LayeredLayout
+import base64
+
+class FlowChart:
+    def __init__(self):
+        # Initialize the flowchart state in session state if it doesn't exist
+        if "flowchart_state" not in st.session_state:
+            st.session_state.flowchart_state = self.create_default_state()
+
+    def create_default_state(self):
+        """Initialize default nodes and edges."""
+        
+        # Convert SVG to Base64 string
+        image_path = "data/img/Deutscher_Bundestag.svg"
+        with open(image_path, "rb") as image_file:
+            image_base64 = base64.b64encode(image_file.read()).decode("utf-8")
+
+        nodes = [
+            # Source
+            StreamlitFlowNode("bundestag",(0, 0), {"content": "Bundestag"}, "input", "right"),
+            StreamlitFlowNode("faz", (0, 0), {'content': "FAZ"}, 'input', 'right'),
+            StreamlitFlowNode("taz", (0, 0), {"content": "taz"}, "input", "right"),
+            StreamlitFlowNode("spiegel", (0, 0), {"content": "Spiegel"}, "input", "right"),
+            StreamlitFlowNode("sz", (0, 0), {"content": "Süddeutsche Zeitung"}, "input", "right"),
+            StreamlitFlowNode("bild", (0, 0), {"content": "Bild"}, "input", "right"),
+            StreamlitFlowNode("zeit", (0, 0), {"content": "zeit"}, "input", "right"),
+            StreamlitFlowNode("nzz", (0, 0), {"content": "Neu Zürcher Zeitung"}, "input", "right"),
+
+            # corpus       
+            StreamlitFlowNode("corpus",(0, 0), {'content': "corpus"}, 'default', 'right', 'left'),
+            # BERTopic
+            StreamlitFlowNode("bertopic",(0, 0), {'content': """### BERToptic"""}, 'default', 'right', 'left'),   
+            # spacy
+            StreamlitFlowNode("spacy",(0, 0), {'content': """### spacy"""}, 'default', 'right', 'left'), 
+            # inception
+            StreamlitFlowNode("inception",(0, 0), {'content': """### INCEpTION"""}, 'default', 'right', 'left'), 
+            # inception
+            StreamlitFlowNode("causalbert",(0, 0), {'content': """### CausalBERT"""}, 'default', 'right', 'left'),     
+
+        ]
+
+        edges = [
+            StreamlitFlowEdge("Bundestag-corpus", "bundestag", "corpus", animated=True),
+            StreamlitFlowEdge("FAZ-corpus", "faz", "corpus", animated=True),
+            StreamlitFlowEdge("taz-corpus", "taz", "corpus", animated=True),
+            StreamlitFlowEdge("spiegel-corpus", "spiegel", "corpus", animated=True),
+            StreamlitFlowEdge("sz-corpus", "sz", "corpus", animated=True),
+            StreamlitFlowEdge("bild-corpus", "bild", "corpus", animated=True),
+            StreamlitFlowEdge("zeit-corpus", "zeit", "corpus", animated=True),
+            StreamlitFlowEdge("nzz-corpus", "nzz", "corpus", animated=True),
+            StreamlitFlowEdge("corpus-BERTopic", "corpus", "bertopic", animated=True),
+            StreamlitFlowEdge("corpus-spacy", "corpus", "spacy", animated=True),
+            StreamlitFlowEdge("spacy-inception", "spacy", "inception", animated=True),
+            StreamlitFlowEdge("inception-causalbert", "inception", "causalbert", animated=True)
+        ]
+        return StreamlitFlowState(nodes, edges)
+
+    def render(self):
+        """Render the flowchart with TreeLayout and restricted interactions."""
+        st.session_state.flowchart_state = streamlit_flow(
+            "markdown_node_flow",
+            st.session_state.flowchart_state,
+            layout=LayeredLayout(direction='right'),
+            fit_view=True,
+            show_minimap=False,
+            show_controls=True,
+            hide_watermark=True,
+            allow_new_edges=False,
+            enable_node_menu=False,
+            enable_edge_menu=False,
+            enable_pane_menu=False
+        )

plot.py

@@ -46,6 +46,7 @@ class Plot:
             )
             fig.update_traces(
                 textposition='inside',
+                insidetextanchor='middle',
                 texttemplate='%{text}',
                 textfont=dict(color='rgb(255, 255, 255)')
             )
@@ -79,6 +80,7 @@ class Plot:
             fig.update_traces(
                 texttemplate='%{y}',
                 textposition='inside',
+                insidetextanchor='middle',
                 textfont=dict(color='rgb(255, 255, 255)')
             )
 
@@ -99,6 +101,7 @@ class Plot:
             fig.update_traces(
                 textposition='inside',
                 texttemplate='%{text}',
+                insidetextanchor='middle',
                 textfont=dict(color='rgb(255, 255, 255)')
             )
 
@@ -129,6 +132,7 @@ class Plot:
         fig.update_traces(
             texttemplate='%{y}',
             textposition='inside',
+            insidetextanchor='middle',
             textfont=dict(color='rgb(255, 255, 255)')
         )
         return fig
@@ -166,18 +170,18 @@ class Plot:
         # Perform UMAP dimensionality reduction
         reducer = umap.UMAP(n_components=2, random_state=42, n_neighbors=50, n_jobs=1, metric='cosine')
         reduced_features = reducer.fit_transform(features_clean)
-        df_reduced = pd.DataFrame(reduced_features, columns=['Component 1', 'Component 2'])
+        df_reduced = pd.DataFrame(reduced_features, columns=['UMAP x', 'UMAP y'])
         df_reduced = pd.concat([df_reduced, metadata.reset_index(drop=True)], axis=1)
 
         # Plotting the scatter plot
-        hover_data = {'cause': True, 'Component 1': False, 'Component 2': False}
+        hover_data = {'cause': True, 'UMAP x': False, 'UMAP y': False}
         if include_modality:
             hover_data['Modality'] = True
 
         fig = px.scatter(
             df_reduced,
-            x='Component 1',
-            y='Component 2',
+            x='UMAP x',
+            y='UMAP y',
             color='subfolder',
             symbol='indicator',
             labels={'subfolder': 'Effect'},